Conjugate descent formulation of backpropagation error in feedforward neural networks
The feedforward neural network architecture uses backpropagation learning to determine optimal weights between different interconnected layers. This learning procedure uses a gradient descent technique applied to a sum-of-squares error function for the given input-output pattern. It employs an itera...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Operations Research Society of South Africa (ORSSA)
2009-06-01
|
| Series: | ORiON |
| Online Access: | http://orion.journals.ac.za/pub/article/view/73 |